Recursive adaptive interaction management system

Abstract

A management system for guiding an agent in a media-specific dialogue has a conversion engine for instantiating ongoing dialogue as machine-readable text, if the dialogue is in voice media, a context analysis engine for determining facts from the text, a rules engine for asserting rules based on fact input, and a presentation engine for presenting information to the agent to guide the agent in the dialogue. The context analysis engine passes determined facts to the rules engine, which selects and asserts to the presentation engine rules based on the facts, and the presentation engine provides periodically updated guidance to the agent based on the rules asserted.

We claim: 
     
       1. A computer-based management system for guiding a human agent during an interaction with a customer of a contact center, comprising:
 a processor; and 
 a memory, wherein the memory has computer instructions stored therein that, when executed by the processor, cause the processor to:
 assemble a first script having first and second components; 
 display the first and second components of the first script on an agent display device during the interaction for guiding the human agent on suggested dialogue or other actions to be taken during the interaction between the agent and the customer; 
 monitor the interaction between the human agent and the customer for context analysis and generate context analysis output in response; 
 monitor real-time statistics of the contact center, wherein the real-time statistics indicate decrease of the contact center performance; 
 determine that the agent has taken an action not anticipated by the first script based on the context analysis output; 
 in response to the determining, dynamically assemble, during the interaction between the human agent and the customer, a second script having third and fourth components, wherein the second script is based on the monitored real-time statistics of the contact center, and is for increasing the contact center performance; and 
 update the agent display device to display the third and fourth components instead of the first and second components. 
 
 
     
     
       2. The system of  claim 1 , wherein the second script is dynamically assembled based on the action not anticipated by the first script. 
     
     
       3. The system of  claim 1 , wherein the instructions further cause the processor to:
 update the context analysis output based on the action; and 
 identify a rule based on the updated context analysis output, wherein the second script is dynamically assembled based on the rule. 
 
     
     
       4. The system of  claim 1 , wherein updating the agent display device to display the third and fourth components of the second script comprises removing the first script from the agent display device. 
     
     
       5. The system of  claim 1 , wherein the interaction is a voice dialog, and the instructions further cause the processor to:
 convert the voice dialog to machine-readable text, wherein the context analysis is based on the machine-readable text. 
 
     
     
       6. The system of  claim 1 , wherein the context analysis is based on analysis of additional data other than text of communication exchanged between the agent and the customer during the interaction. 
     
     
       7. The system of  claim 6 , wherein the additional data includes one or more of volume of speech, vocal inflection, sentence structure, or rate of dialogue. 
     
     
       8. The system of  claim 1 , wherein the other actions are actions other than a response to the customer, to be taken during the interaction between the human agent and the customer. 
     
     
       9. The system of  claim 1 , wherein the second script includes prompts that are annotated with indicia indicating characteristics of the prompts. 
     
     
       10. The system of  claim 1 , wherein the action not anticipated by the first script includes a change of topic of the interaction between the human agent and the customer. 
     
     
       11. A method of guiding a human agent during an interaction with a customer of a contact center, comprising:
 assembling, by a processor, a first script having first and second components; 
 displaying, by the processor, the first and second components of the first script on an agent display device during the interaction for guiding the human agent on suggested dialogue or other actions to be taken during the interaction between the agent and the customer; 
 monitoring, by the processor, the interaction between the human agent and the customer for context analysis and generate context analysis output in response; 
 monitoring, by the processor, real-time statistics of the contact center, wherein the real-time statistics indicate decrease of the contact center performance; 
 determining, by the processor, that the agent has taken an action not anticipated by the first script based on the context analysis output; 
 in response to the determining, dynamically assembling, by the processor, during the interaction between the human agent and the customer, a second script having third and fourth components, wherein the second script is based on the monitored real-time statistics of the contact center, and is for increasing the contact center performance; and 
 updating, by the processor, the agent display device to display the third and fourth components instead of the first and second components. 
 
     
     
       12. The method of  claim 11 , wherein the second script is dynamically assembled based on the action not anticipated by the first script. 
     
     
       13. The method of  claim 11 , further comprising:
 updating, by the processor, the context analysis output based on the action; and 
 identifying, by the processor, a rule based on the updated context analysis output, wherein the second script is dynamically assembled based on the rule. 
 
     
     
       14. The method of  claim 11 , wherein updating the agent display device to display the third and fourth components of the second script comprises removing the first script from the agent display device. 
     
     
       15. The method of  claim 11 , wherein the interaction is a voice dialog, the method further comprising:
 converting, by the processor, the voice dialog to machine-readable text, wherein the context analysis is based on the machine-readable text. 
 
     
     
       16. The method of  claim 11 , wherein the context analysis is based on analysis of additional data other than text of communication exchanged between the agent and the customer during the interaction. 
     
     
       17. The method of  claim 16 , wherein the additional data includes one or more of volume of speech, vocal inflection, sentence structure, or rate of dialogue. 
     
     
       18. The method of  claim 11 , wherein the other actions are actions other than a response to the customer, to be taken during the interaction between the human agent and the customer. 
     
     
       19. The method of  claim 11 , wherein the second script includes prompts that are annotated with indicia indicating characteristics of the prompts.